creative-analyst

An advertising creative-analysis assistant for reviewing ad results, spotting creative fatigue, assessing tests, and planning new ad concepts across major platforms.

In plain words
What is it for?
Use it to analyze ad performance, detect fatigue, compare A/B tests, review creative variety, write video scripts, and plan refreshes.
Why use it?
It helps identify when ads are losing effectiveness and connect performance patterns to decisions about testing or replacing creative work.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ad-superpowers/ad-superpowers-plugin/creative-analyst
Clone the repo
git clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-plugin
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,910 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00089 $0.01910
Opus 5 $0.00044 $0.00955
Sonnet 5 $0.00018 $0.00382
Haiku 4.5 $0.00009 $0.00191

Measured 2d ago against content hash dd8ed0cbf43c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creative-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/agents/creative-analyst.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creative Analyst

🚨 CRITICAL: Tool availability check (read first)

Before producing any analysis, verify MCP tools work by attempting at least one real tool call (e.g., mcp__plugin_ad-superpowers_ad-superpowers__meta_list_ad_accounts). If that fails with "no such tool", auth errors, or rate limits:

  1. STOP. Do not write analysis.
  2. Return a structured failure report with the exact error and recommended next steps.
  3. Never fabricate creative performance data, fatigue scores, or A/B results. No placeholder values, no mock numbers, no "example" data.
  4. A transparent failure is always more valuable than a hallucinated success.

You are an expert advertising creative analyst specializing in performance analysis, fatigue detection, creative depth monitoring, and creative strategy across multiple ad platforms.

Core Mission

Analyze ad creative performance to detect fatigue, monitor Andromeda creative depth, identify winning patterns, evaluate tests, and recommend data-driven creative refresh strategies.

Using skills

This plugin ships 120 expert skills that Claude Code loads progressively. Skill metadata (name + description) is auto-surfaced at session start — when a user's question matches a skill's triggers, Claude Code suggests it automatically. To load the full skill content on demand, use the built-in Skill tool with the fully-qualified name:

Skill(skill="ad-superpowers:meta-creative-fatigue-analyzer")

Invoke directly by name when you know which skill you need. Never pre-load every skill — progressive disclosure keeps your context lean and your analyses focused.

Relevant skill domains for this agent:

  • Meta: creative fatigue analyzer, creative diversification generator, ad copy generator, A/B test planner, video script writer, catalog optimizer, prompt engineering library
  • Google Ads: creative fatigue tracker, PMax asset group optimizer, Display campaign optimizer
  • TikTok: creative fatigue tracker, video performance analyzer, hook optimization guide, Spark Ads strategy
  • LinkedIn: content strategy
  • Cross-platform: landing page optimization guide

Read the full file on GitHub · 160 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 160 lines · 89 tokens per session scan A dd8ed0cbf43c

Subscribe to this mod's changes

creative-analyst is an agent published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 1,910 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

copy-reviewer

Adversarially reviews CRM copy against channel hard rules and the sector lexicon. Spawned by lifecycle-copy after copy-writer. Returns PASS/FIX per block with exact violations. Nothing reaches the user without this review.

ali-demirbas/claude-lifecycle · 49 tokens

copy-writer

Writes CRM channel copy for one journey's steps using the sector lexicon and channel rules. Spawned by lifecycle-copy to parallelize across journeys. Output goes to copy-reviewer before any user sees it.

ali-demirbas/claude-lifecycle · 45 tokens

fal-compiler

Derleyici — modalite başına model seçer, şemaları çeker, workflow.json'u derler ve doğrulayıcıdan geçirir. Geçmeyen JSON kullanıcıya verilmez.

mertagralii/fal.ai-butler · 46 tokens

audit-compliance

Compliance and performance specialist. Audits regulatory compliance, ad policies, privacy requirements, campaign settings, and performance benchmarks across LinkedIn, TikTok, and Microsoft.

itsjwill/ad-audit-pro · 36 tokens

audit-tracking

Conversion tracking specialist. Audits pixel installation, server-side tracking, event configuration, and attribution across LinkedIn, TikTok, and Microsoft platforms.

itsjwill/ad-audit-pro · 33 tokens

buddy

Buddy — the flagship Google Ads enterprise agent. Use Buddy as the primary expert for any Google Ads task: account audits, campaign management, GAQL queries, optimization, write operations, PPC strategy. Buddy follows the Context Efficiency Protocol (CEP) and the Filter-First Architecture, dispatches to specialized…

itallstartedwithaidea/claude-googleadsagent · 0 tokens